benchlm.ai

Qwen2.5-1M vs Qwen3 235B 2507

Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.

Quick Verdict

Qwen2.5-1M wins overall with a score of 66 vs 30 (36 point difference).Qwen2.5-1M wins 4 out of 4 categories.

Qwen2.5-1M

CreatorAlibaba
TypeOpen Weight
Context1M
Score66

Qwen3 235B 2507

CreatorAlibaba
TypeOpen Weight
Context128K
Score30

Knowledge

Qwen2.5-1M

Qwen2.5-1M

81.8

Qwen3 235B 2507

36.8

84
MMLU
39
83
GPQA
38
81
SuperGPQA
36
79
OpenBookQA
34

Coding

Qwen2.5-1M

Qwen2.5-1M

76

Qwen3 235B 2507

31

76
HumanEval
31

Mathematics

Qwen2.5-1M

Qwen2.5-1M

84

Qwen3 235B 2507

38

85
AIME 2023
39
87
AIME 2024
41
86
AIME 2025
40
81
HMMT Feb 2023
35
83
HMMT Feb 2024
37
82
HMMT Feb 2025
36
84
BRUMO 2025
38

Reasoning

Qwen2.5-1M

Qwen2.5-1M

80

Qwen3 235B 2507

36

81
SimpleQA
37
79
MuSR
35

Frequently Asked Questions

Which is better, Qwen2.5-1M or Qwen3 235B 2507?

Qwen2.5-1M scores higher overall with 66 vs 30, a difference of 36 points across all benchmarks.

Which is better for knowledge tasks, Qwen2.5-1M or Qwen3 235B 2507?

Qwen2.5-1M leads in knowledge tasks with an average score of 81.8 vs 36.8.

Which is better for coding, Qwen2.5-1M or Qwen3 235B 2507?

Qwen2.5-1M leads in coding with an average score of 76 vs 31.

Which is better for math, Qwen2.5-1M or Qwen3 235B 2507?

Qwen2.5-1M leads in math with an average score of 84 vs 38.

Which is better for reasoning, Qwen2.5-1M or Qwen3 235B 2507?

Qwen2.5-1M leads in reasoning with an average score of 80 vs 36.

Related Comparisons

Qwen2.5-1M vs GPT-5.4Qwen2.5-1M vs Gemini 3.1 ProQwen2.5-1M vs Claude Opus 4.6Qwen2.5-1M vs GPT-5.3 CodexQwen2.5-1M vs Grok 4.1Qwen2.5-1M vs GPT-5.2